Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
2007-04-24
2007-04-24
Lerner, Martin (Department: 2626)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
C704S243000, C704S256200
Reexamination Certificate
active
10323990
ABSTRACT:
Noise-superimposed speech data is grouped according to acoustic similarity, and sufficient statistics are prepared using the speech data in each of the groups. A group acoustically similar to voice data of a user of the speech recognition is selected, and sufficient statistics acoustically similar to the user's voice data are selected from the sufficient statistics in the selected group. Using the selected sufficient statistics, an acoustic model is prepared.
REFERENCES:
patent: 5819223 (1998-10-01), Takagi
patent: 5839105 (1998-11-01), Ostendorf et al.
patent: 5864810 (1999-01-01), Digalakis et al.
patent: 6336108 (2002-01-01), Thiesson et al.
patent: 6389393 (2002-05-01), Gong
patent: 6421641 (2002-07-01), Huang et al.
patent: 6466908 (2002-10-01), Baggenstoss
patent: 6622117 (2003-09-01), Deligne et al.
patent: 6804647 (2004-10-01), Heck et al.
patent: 6842734 (2005-01-01), Yamada et al.
patent: 6876966 (2005-04-01), Deng et al.
patent: 7065487 (2006-06-01), Miyazawa
patent: 7103541 (2006-09-01), Attias et al.
patent: 2003/0050783 (2003-03-01), Yoshizawa
patent: 2003/0200085 (2003-10-01), Nguyen et al.
patent: 2004/0002858 (2004-01-01), Attias et al.
patent: 2004/0019483 (2004-01-01), Deng et al.
patent: 2004/0143435 (2004-07-01), Deng et al.
patent: 2005/0228666 (2005-10-01), Liu et al.
patent: 05002399 (1993-01-01), None
patent: 06-214592 (1994-08-01), None
patent: 09-034485 (1997-02-01), None
patent: 09-258769 (1997-10-01), None
patent: 10-161692 (1998-06-01), None
patent: 10-512686 (1998-12-01), None
patent: 11-175090 (1999-07-01), None
patent: 2000-075889 (2000-03-01), None
patent: 2000-081893 (2000-03-01), None
patent: 2000-330587 (2000-11-01), None
patent: 2001-255887 (2001-09-01), None
patent: 2002-182682 (2002-06-01), None
Yoshizawa et al., “Unsupervised speaker adaptation based on sufficient HMM statistics of selected speakers,” IEEE International Conference on Acoustics, Speech, and Signal Processing, 2001, May 7-11, 2001, vol. 1, pp. 341-344.
Wang et al., “Complete recognition of continuous Mandarin speech for Chinese language with very large vocabulary but limited training data,” Conference on Acoustics, Speech, and Signal Processing, 1995. ICASSP-95. May 9-12, 1995, vol. 1, pp. 61 to 64.
Nakamura et al., “Noise and room acoustics distorted speech recognition by HMM composition,” 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. May 7-10, 1996, vol. 1, pp. 69 to 72.
Shinichi Yoshizawa et al.; “Unsupervised training based on the sufficient HMM statistics from selected speakers”; Technical Report of IEICE; NLC2000-41, SP2000-89 (Dec. 2000); pp. 83-88.
M.J.F. Gales; “Cluster Adaptive Training for Speech Recognition”; IBM T.J. Watson Research Center; Yorktown Heights, New York.
Masahiro Tanaka; “Principle and Application of EM Algorithm”; System/Control/Information; The Institute of Systems, Control and Information Engineers; vol. 42, No. 2; 1998; pp. 88-96; with a partial English translation.
Gao Y et al: “Speaker Adaptation Based on Pre-Clustering Training Speakers” 5th European Conference on Speech Communication and Technology. Eurospeech '97. Rhodes, Greece, Sep. 22-25, 1997.
Illina I et al: “Environment normalization training and environment adaptation using mixture stochastic trajectory model” Speech Communication, Elsevier Science Publishers, Amsterdam, NL, vol. 26, No. 4, Dec. 1998.
Wu C et al: “Speaker adaptation for telephony data using speaker clustering” Proceedings of the International Conference on Signal Processing, vol. 2, Aug. 21, 2000.
Shikano Kiyohiro
Yoshizawa Shinichi
Harness & Dickey & Pierce P.L.C.
Lerner Martin
LandOfFree
Preparing acoustic models by sufficient statistics and... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Preparing acoustic models by sufficient statistics and..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Preparing acoustic models by sufficient statistics and... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3784979